Data points: 122
Model compare
The readout for GPT-4.1 and GPT-5.1, before the detailed comparison sheet.
Weighted outcome: GPT-5.1. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
GPT-5.1
GPT-5.1 has the higher weighted result; Model A / B score 17.3 to 82.7.
Evidence depth
122 data points
Includes 26 benchmark rows, 1 audit samples, and 6 provider examples.
Selection signal
Start with GPT-5.1
The charts below split 33 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for GPT-4.1 and GPT-5.1: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | GPT-4.1 | GPT-5.1 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 17.3 pts | 82.7 pts |
| Benchmark category leads | 1 categories | 5 categories |
| Operational advantages | First-token latency | Cheapest input price, Average speed, Free providers, Provider coverage |
| Context window | 1.0M tokens | 400K tokens |
| Max output | 32.8K tokens | 128K tokens |
| Modalities | Input ImageTextFile Output Text |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | GPT-4.1 | GPT-5.1 |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | Apr 2025 | Nov 2025 |
| Parameters | No data | No data |
| Tokenizer | GPT | GPT |
| Knowledge cutoff | 2024-06-30 | No data |
| OpenRouter ID | openai/gpt-4.1 | openai/gpt-5.1 |
| References | No data | No data |
This report only uses LMSpeed data for GPT-4.1 and GPT-5.1: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
GPT-4.1
GPT-4.1 is stronger in benchmark categories (Knowledge) and operational dimensions (First-token latency).
GPT-5.1
GPT-5.1 is stronger in benchmark categories (Agents, Coding, Reasoning, Math, Instruction following) and operational dimensions (Cheapest input price, Average speed, Free providers, Provider coverage).
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
GPT-4.1
46
Avg. score
GPT-5.1
52.1
GPT-5.1 leads by 8.3
GPT-5.1 leads by 10.6
GPT-5.1 leads by 3.6
GPT-4.1 leads by 2.8
GPT-5.1 leads by 5.0
No data
No data
GPT-5.1 leads by 11.8
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
GPT-4.1
46.0
Rank #65/83 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner56.0
Rank #44/83 · confidence 1 · eval date 2025-11-13
GPT-4.1
winner0.56 s
Rank #18/136 · confidence 4
GPT-5.1
35.90 s
Rank #113/136 · confidence 4
GPT-4.1
winner0.56 s
Rank #25/136 · confidence 4
GPT-5.1
35.90 s
Rank #128/136 · confidence 4
GPT-4.1
winner150.8 tok/s
Rank #41/136 · confidence 4
GPT-5.1
111.6 tok/s
Rank #60/136 · confidence 4
GPT-4.1
$2.00/M
Rank #124/162 · confidence 4
GPT-5.1
winner$1.25/M
Rank #108/162 · confidence 4
GPT-4.1
winner$8.00/M
Rank #115/162 · confidence 4
GPT-5.1
$10.00/M
Rank #121/162 · confidence 4
GPT-4.1
$3.50/M
Rank #124/162 · confidence 4
GPT-5.1
winner$3.44/M
Rank #118/162 · confidence 4
GPT-4.1
61.0
Rank #56/89 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner75.0
Rank #3/89 · confidence 1 · eval date 2025-11-13
GPT-4.1
80.6%
Rank #57/125 · confidence 4
GPT-5.1
winner87.0%
Rank #12/125 · confidence 4
GPT-4.1
66.6%
Rank #125/187 · confidence 4
GPT-5.1
winner87.3%
Rank #32/187 · confidence 4
GPT-4.1
4.6%
Rank #141/186 · confidence 4
GPT-5.1
winner26.5%
Rank #39/186 · confidence 4
GPT-4.1
45.7%
Rank #65/115 · confidence 4
GPT-5.1
winner86.8%
Rank #4/115 · confidence 4
GPT-4.1
38.1%
Rank #90/184 · confidence 4
GPT-5.1
winner43.3%
Rank #41/184 · confidence 4
GPT-4.1
38.1
Rank #67/96 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner43.3
Rank #45/96 · confidence 1 · eval date 2025-11-13
GPT-4.1
5.5
Rank #37/47 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner31.0
Rank #19/47 · confidence 1 · eval date 2025-11-13
GPT-4.1
28.3
Rank #47/56 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner49.9
Rank #30/56 · confidence 1 · eval date 2025-11-13
GPT-4.1
24.2
Rank #62/90 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner37.6
Rank #31/90 · confidence 1 · eval date 2025-11-13
GPT-4.1
66.6
Rank #80/96 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner87.3
Rank #36/96 · confidence 1 · eval date 2025-11-13
GPT-4.1
4.6
Rank #82/96 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner26.5
Rank #39/96 · confidence 1 · eval date 2025-11-13
GPT-4.1
winner79.6
Rank #42/90 · confidence 1 · eval date 2025-04-14
GPT-5.1
51.3
Rank #66/90 · confidence 1 · eval date 2025-11-13
GPT-4.1
19.4
Rank #76/99 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner36.9
Rank #42/99 · confidence 1 · eval date 2025-11-13
GPT-4.1
61.2
Rank #49/57 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner75.5
Rank #23/57 · confidence 1 · eval date 2025-11-13
GPT-4.1
1071.0
Rank #57/65 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner1220.0
Rank #37/65 · confidence 1 · eval date 2025-11-13
GPT-4.1
43.0
Rank #64/86 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner72.9
Rank #30/86 · confidence 1 · eval date 2025-11-13
GPT-4.1
25.6
Rank #50/50 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner41.2
Rank #35/50 · confidence 1 · eval date 2025-11-13
GPT-4.1
47.1
Rank #68/84 · confidence 1 · eval date 2025-04-14
GPT-5.1
winner81.9
Rank #52/84 · confidence 1 · eval date 2025-11-13
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-4.1 | GPT-5.1 |
|---|---|---|
Winner: GPT-4.1 | GPT-4.1 gpt-4.1 Audit score 78 70728088 | GPT-5.1 gpt-5-1 No audit yet |
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GPT-4.1 | GPT-5.1 |
|---|---|---|
120 tests | GPT-4.1 speed / latency 81 tok/s / 1822ms input / output No data | GPT-5.1 speed / latency N/A / N/A input / output No data |
10 tests | GPT-4.1 speed / latency N/A / N/A input / output No data | GPT-5.1 speed / latency 137 tok/s / 3299ms input / output No data |
5 tests | GPT-4.1 speed / latency 79 tok/s / 2301ms input / output No data | GPT-5.1 speed / latency N/A / N/A input / output No data |
5 tests | GPT-4.1 speed / latency N/A / N/A input / output No data | GPT-5.1 speed / latency 96 tok/s / 1862ms input / output No data |
0 tests | GPT-4.1 speed / latency N/A / N/A input / output No data | GPT-5.1 speed / latency N/A / N/A input / output No data |
GPT-4.1 gpt-4.1 speed / latency No data input / output $0/request | GPT-5.1 gpt-5.1 speed / latency No data input / output $0/request |
Weighted outcome: GPT-5.1. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Input
Output
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON mode | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
